NamSor recognizes the likely cultural origin and gender at the same time, for higher precision and recall.
Global coverage :
NamSor covers all languages, alphabets, countries, regions. We constantly improve the precision, working with linguists, anthropologist and historians. We can recognize, for example, the gender of Indian names in scripts such as
TELUGU, ORIYA, GURMUKHI, MALAYALAM, BENGALI, GUJARATI, KANNADA, DEVANAGARI, TAMIL, ARABIC, LATIN. We can recognize, for example, the Armenian origin of names in CYRILLIC, GEORGIAN, ARMENIAN, ARABIC, LATIN. Other examples:
Ease of use: names can be parsed and classified online, using a simple web application that processes up to 100,000 names within a few minutes. Power users, statisticians and data scientists can take benefit of NamSor open source extension for RapidMiner, a leading predictive analytics tool. NamSor API can be securely integrated with a range of applications, from geographical information systems (such as ESRI), to CRM and campaign management.
Fine grained: NamSor API currently supports several taxonomies for general use. We also design specific taxonomies calibrated at a finer grained level (regional dialects, ethnicity, casts or clanic systems) for the use of academic researchers and the specific needs of international organizations (migration studies, international aid, diaspora marketing and fundraising: see our tailored services).